Testing for a Threshold in Models with Endogenous Regressors

Research output: Working paperDiscussion paperOther research output

Abstract

Using 2SLS estimation, we propose two tests for a threshold in models with
endogenous regressors: a sup LR test and a sup Wald test. Here, the 2SLS estimation is not conventional because it uses additional information about the first-stage being linear or not. Because of this additional information, our tests can be more accurate than the threshold test in Caner and Hansen (2004) which is based on conventional GMM estimation.
We derive the asymptotic distributions of the two tests for a linear and for a threshold reduced form. In both cases, the distributions are non-pivotal, and we propose obtaining critical values via a fixed regressor wild bootstrap.
Our simulations show that in small samples, the GMM test of Caner and Hansen (2004) can be severely oversized under heteroskedasticity, while the 2SLS tests we propose are much closer to their nominal size.
We use our tests to investigate the common claim that the government spending multiplier is larger close to the zero lower bound, and therefore that the governments should have spent more in the recent crisis. We find no empirical support for this claim.
LanguageEnglish
Place of PublicationTilburg
PublisherCentER, Center for Economic Research
Number of pages73
Volume2016-029
Publication statusPublished - 3 Aug 2016

Publication series

NameCentER Discussion Paper
Volume2016-029

Fingerprint

Endogenous regressors
Testing
Multiplier
Wald test
Zero lower bound
Asymptotic distribution
Information use
Simulation
Reduced form
Critical value
GMM estimation
Small sample
Government
Wild bootstrap
Heteroskedasticity
Government spending

Keywords

  • 2SLS
  • GMM
  • threshold tests
  • wild bootstrap

Cite this

Rothfelder, M., & Boldea, O. (2016). Testing for a Threshold in Models with Endogenous Regressors. (CentER Discussion Paper; Vol. 2016-029). Tilburg: CentER, Center for Economic Research.
Rothfelder, Mario ; Boldea, Otilia. / Testing for a Threshold in Models with Endogenous Regressors. Tilburg : CentER, Center for Economic Research, 2016. (CentER Discussion Paper).
@techreport{40ca581ae22849ae911fea707ff4209c,
title = "Testing for a Threshold in Models with Endogenous Regressors",
abstract = "Using 2SLS estimation, we propose two tests for a threshold in models withendogenous regressors: a sup LR test and a sup Wald test. Here, the 2SLS estimation is not conventional because it uses additional information about the first-stage being linear or not. Because of this additional information, our tests can be more accurate than the threshold test in Caner and Hansen (2004) which is based on conventional GMM estimation.We derive the asymptotic distributions of the two tests for a linear and for a threshold reduced form. In both cases, the distributions are non-pivotal, and we propose obtaining critical values via a fixed regressor wild bootstrap. Our simulations show that in small samples, the GMM test of Caner and Hansen (2004) can be severely oversized under heteroskedasticity, while the 2SLS tests we propose are much closer to their nominal size.We use our tests to investigate the common claim that the government spending multiplier is larger close to the zero lower bound, and therefore that the governments should have spent more in the recent crisis. We find no empirical support for this claim.",
keywords = "2SLS, GMM, threshold tests, wild bootstrap",
author = "Mario Rothfelder and Otilia Boldea",
year = "2016",
month = "8",
day = "3",
language = "English",
volume = "2016-029",
series = "CentER Discussion Paper",
publisher = "CentER, Center for Economic Research",
type = "WorkingPaper",
institution = "CentER, Center for Economic Research",

}

Rothfelder, M & Boldea, O 2016 'Testing for a Threshold in Models with Endogenous Regressors' CentER Discussion Paper, vol. 2016-029, CentER, Center for Economic Research, Tilburg.

Testing for a Threshold in Models with Endogenous Regressors. / Rothfelder, Mario; Boldea, Otilia.

Tilburg : CentER, Center for Economic Research, 2016. (CentER Discussion Paper; Vol. 2016-029).

Research output: Working paperDiscussion paperOther research output

TY - UNPB

T1 - Testing for a Threshold in Models with Endogenous Regressors

AU - Rothfelder, Mario

AU - Boldea, Otilia

PY - 2016/8/3

Y1 - 2016/8/3

N2 - Using 2SLS estimation, we propose two tests for a threshold in models withendogenous regressors: a sup LR test and a sup Wald test. Here, the 2SLS estimation is not conventional because it uses additional information about the first-stage being linear or not. Because of this additional information, our tests can be more accurate than the threshold test in Caner and Hansen (2004) which is based on conventional GMM estimation.We derive the asymptotic distributions of the two tests for a linear and for a threshold reduced form. In both cases, the distributions are non-pivotal, and we propose obtaining critical values via a fixed regressor wild bootstrap. Our simulations show that in small samples, the GMM test of Caner and Hansen (2004) can be severely oversized under heteroskedasticity, while the 2SLS tests we propose are much closer to their nominal size.We use our tests to investigate the common claim that the government spending multiplier is larger close to the zero lower bound, and therefore that the governments should have spent more in the recent crisis. We find no empirical support for this claim.

AB - Using 2SLS estimation, we propose two tests for a threshold in models withendogenous regressors: a sup LR test and a sup Wald test. Here, the 2SLS estimation is not conventional because it uses additional information about the first-stage being linear or not. Because of this additional information, our tests can be more accurate than the threshold test in Caner and Hansen (2004) which is based on conventional GMM estimation.We derive the asymptotic distributions of the two tests for a linear and for a threshold reduced form. In both cases, the distributions are non-pivotal, and we propose obtaining critical values via a fixed regressor wild bootstrap. Our simulations show that in small samples, the GMM test of Caner and Hansen (2004) can be severely oversized under heteroskedasticity, while the 2SLS tests we propose are much closer to their nominal size.We use our tests to investigate the common claim that the government spending multiplier is larger close to the zero lower bound, and therefore that the governments should have spent more in the recent crisis. We find no empirical support for this claim.

KW - 2SLS

KW - GMM

KW - threshold tests

KW - wild bootstrap

M3 - Discussion paper

VL - 2016-029

T3 - CentER Discussion Paper

BT - Testing for a Threshold in Models with Endogenous Regressors

PB - CentER, Center for Economic Research

CY - Tilburg

ER -

Rothfelder M, Boldea O. Testing for a Threshold in Models with Endogenous Regressors. Tilburg: CentER, Center for Economic Research. 2016 Aug 3. (CentER Discussion Paper).